Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1721 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0861. Min Act: -0.0005
Data Index: 1525725 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0806. Min Act: -0.0005
Data Index: 334403 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0814. Min Act: -0.0005
Data Index: 1607576 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0807. Min Act: -0.0005
Data Index: 1382598 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0724. Min Act: -0.0005
Data Index: 1418343 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0690. Min Act: -0.0005
Data Index: 390246 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0663. Min Act: -0.0005
Data Index: 507740 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0647. Min Act: -0.0005
Data Index: 1613383 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0632. Min Act: -0.0005
Data Index: 1478633 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0674. Min Act: -0.0005
Data Index: 1485595 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0656. Min Act: -0.0005
Data Index: 296964 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0605. Min Act: -0.0005
Data Index: 1397966 (Python Code)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0629. Min Act: -0.0005
Data Index: 1464580 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0624. Min Act: -0.0005
Data Index: 1279588 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0656. Min Act: -0.0005
Data Index: 1628737 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0626. Min Act: -0.0005
Data Index: 5859 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0574. Min Act: -0.0005
Data Index: 1425076 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0619. Min Act: -0.0005
Data Index: 690619 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0622. Min Act: -0.0005
Data Index: 1625904 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0861. Min Range: -0.0861
Max Act: 0.0584. Min Act: -0.0005
Data Index: 1552553 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19